对比训练的编码器最近被证明可以反演数据生成过程:它们将每个输入(例如图像)编码为生成该图像的真实潜变量向量(Zimmermann et al., 2021)。然而,现实世界的观测往往具有固有的模糊性。例如,图像可能模糊,或者只显示3D对象的2D视图,因此多个潜变量可能生成它们。这使得潜变量向量的真实后验具有概率性,并带有异方差不确定性。在这种设置下,我们扩展了常见的InfoNCE目标和编码器,以预测潜变量分布而不是点。我们证明,这些分布恢复了数据生成过程的正确后验,包括其偶然不确定性水平,直至潜空间的旋转。除了提供校准的不确定性估计外,这些后验还允许在图像检索中计算可信区间。它们包含与给定查询具有相同潜变量的图像,受限于其不确定性。代码可在https://github.com/mkirchhof/Probabilistic_Contrastive_Learning获取。
英文摘要:
Contrastively trained encoders have recently been proven to invert the data-generating process: they encode each input, e.g., an image, into the true latent vector that generated the image (Zimmermann et al., 2021). However, real-world observations often have inherent ambiguities. For instance, images may be blurred or only show a 2D view of a 3D object, so multiple latents could have generated them. This makes the true posterior for the latent vector probabilistic with heteroscedastic uncertainty. In this setup, we extend the common InfoNCE objective and encoders to predict latent distributions instead of points. We prove that these distributions recover the correct posteriors of the data-generating process, including its level of aleatoric uncertainty, up to a rotation of the latent space. In addition to providing calibrated uncertainty estimates, these posteriors allow the computation of credible intervals in image retrieval. They comprise images with the same latent as a given query, subject to its uncertainty. Code is available at https://github.com/mkirchhof/Probabilistic_Contrastive_Learning
SimCLAD: A Simple Framework for Contrastive Learning of Acronym Disambiguation
College of Electrical and Information Engineering, Hunan University(湖南大学电气与信息工程学院);National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy Sciences(中国科学院自动化研究所模式识别国家重点实验室);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)
Weakly-Supervised Contrastive Learning for Imprecise Class Labels
School of Computer Science and Engineering, Southeast University, Nanjing, China(计算机科学与工程学院,东南大学,南京,中国);Key Laboratory of Computer Network and Information Integration (Southeast University), Ministry of Education, China(计算机网络与信息集成重点实验室(东南大学),教育部,中国)
PRCL: Probabilistic Representation Contrastive Learning for Semi-Supervised Semantic Segmentation
School of Computer Science and Engineering, Northeastern University(东北大学计算机科学与工程学院);Intelligent Game and Decision Laboratory(智能游戏与决策实验室);Alibaba DAMO Academy, Alibaba Group(阿里巴巴集团达摩院);Zhejiang University(浙江大学)
Contrastive Rendering for Ultrasound Image Segmentation
School of Biomedical Engineering, Health Center, Shenzhen University(深圳大学生物医学工程学院、健康中心);Medical UltraSound Image Computing (MUSIC) Lab, Shenzhen University(深圳大学医学超声图像计算(MUSIC)实验室);School of Biological Sciences and Medical Engineering, Southeast University(东南大学生物科学与医学工程学院)
Enhancing Contrastive Learning for Geolocalization by Discovering Hard Negatives on Semivariograms
Professorship Big Geospatial Data Management, Technical University of Munich Germany(技术大学慕尼黑大数据地理空间管理教授职位);University of Maine United States(缅因大学);University of the Bundeswehr Munich Germany(联邦国防军大学慕尼黑)
CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries
Beijing Key Laboratory of Embodied Intelligence Systems, Department of Automation, Tsinghua University, Beijing, China(北京智能体智能系统重点实验室,自动化系,清华大学,北京,中国);The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China(复杂系统认知与决策智能重点实验室,自动化研究所,中国科学院,北京,中国)
Fine-Grained Uncertainty Quantification via Collisions
Department of Electrical and Computer Engineering, The University of Arizona(电气与计算机工程系,亚利桑那大学);Pacific Northwest National Laboratory(太平洋西北国家实验室);Marvell Technology Inc.(Marvell技术公司)
School of Computer Science and Technology, Beijing Institute of Technology(北京理工大学计算机科学与技术学院);School of Computer Science, Beijing University of Posts and Telecommunications(北京邮电大学计算机学院);Department of Computer Science, Tongji University(同济大学计算机科学系);State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications(北京邮电大学网络与交换技术国家重点实验室)
Contrastive uncertainty learning for robust multi-structure segmentation in lower-pelvic MR
UCL Hawkes Institute, University College London(伦敦大学学院霍克斯研究所);Department of Medical Physics and Biomedical Engineering, University College London(伦敦大学学院医学物理与生物医学工程系);Centre for Bioengineering, School of Engineering and Materials Science, Queen Mary University of London(伦敦大学玛丽女王学院工程与材料科学学院生物工程中心);Digital Environment Research Institute, Queen Mary University of London(伦敦大学玛丽女王学院数字环境研究所);Department of Computer Science, University College London(伦敦大学学院计算机科学系)
Spatial-Related Sensors Matters: 3D Human Motion Reconstruction Assisted with Textual Semantics
Beijing Advanced Innovation Center for Materials Genome Engineering(北京材料基因组工程先进创新中心);University of Science and Technology Beijing(北京科技大学);Key Laboratory of Intelligent Bionic Unmanned Systems, Ministry of Education(智能仿生无人系统教育部重点实验室);Institute of Materials Intelligent Technology, Liaoning Academy of Materials(辽宁材料实验室材料智能技术研究所)
Learning Pole Structures of Hadronic States using Predictive Uncertainty Estimation
LIACS, Universiteit Leiden, Niels Bohrweg 1, 2333 CA Leiden, Netherlands(莱顿大学LIACS);National Institute of Physics, University of the Philippines Diliman, Quezon City 1101, Philippines(菲律宾大学Diliman物理研究院);Institute for Complex Quantum Systems, Ulm University, 89069 Ulm, Germany(乌尔姆大学复杂量子系统研究所);Center for Integrated Quantum Science(集成量子科学中心);Instituut-Lorentz, Universiteit Leiden, Niels Bohrweg 2, 2333 CA Leiden, Netherlands(莱顿大学Lorentz研究所)